Generates the matching model that is used by the tMatchPredict component to automatically predict the labels for the suspect pairs and groups records which match the label(s) set in the component properties.
tMatchModel reads the sample of the suspect pairs outputted by tMatchPairing after you label each second element in a pair, analyzes the data using the Random Forest algorithm and generates a matching model.
You can use the sample suspect records labeled in a Grouping campaign defined in Talend Data Stewardship with tMatchModel.
This component runs with Apache Spark 1.6.0 and later versions.
For more technologies supported by Talend, see Talend components.